What we measure, how we measure it, and the current state of the measurement — without the "73% accuracy" slogans that typically come without sources.
Honest disclosure. DeepVane's math stack (multi-factor ensemble, BOCPD regime posterior, copula-blended Markowitz, bin-conditional conformal intervals, Kalman dynamic exposures) deployed to production in April 2026. Forward-return tracking begins 2026-05-16 — the first date a full 30-day forward-return window is available for calibration. Until then, all displayed numbers are either (a) live pipeline diagnostics, or (b) the academic effect sizes from the cited literature. Nothing on this page is an in-sample backtest result dressed up as out-of-sample performance.
Current state
Universe
234/234
234 of 234 tickers refreshed in the last 24 hours.
Regime detection
risk_on
BOCPD posterior as of 2026-04-24. Fires continuously on SPY returns.
Effective breadth
55%
Grinold-Kahn effective count of independent factors out of 12 raw. Low ratio = factors are redundant; high ratio = genuinely different signals.
Tail-dependence
177 pairs
Max upper-tail alignment 0.412. Non-parametric co-crash probability per factor pair, per regime.
Prediction intervals
Prior
Using literature prior width; bin calibration activates after 2026-05-16 when residuals accumulate.
Factor weights
Literature prior
Prior weights are the Asness-Moskowitz-Pedersen + Novy-Marx + Sloan literature defaults. Activates after forward returns accumulate.
Metrics we will publish (from 2026-05-16)
The following metrics become meaningful once forward returns exist for at least one full 30-day horizon. Each is standard in the quant-research literature and will be shown per-regime, per-pattern, and aggregated.
Information Coefficient (IC)
Spearman rank correlation between the composite score and realised forward returns. Published per factor, per regime, per horizon. Honest out-of-sample IC for a strong multi-factor signal is typically 0.03-0.06.
Sharpe ratio
Annualised return / annualised volatility of a long/short decile portfolio formed on the composite. Top quint institutional strategies: 0.8-1.2.
Max drawdown
Peak-to-trough decline of the same portfolio. Tracked with and without the conformal-interval-based position-sizing overlay.
Conformal coverage
Fraction of tickers whose realised forward return falls within the published prediction interval. Target: 90% (matches the stated α = 0.1).
Per-pattern hit rate
For each of the 15 patterns, fraction of fires that deliver the expected-direction return over the pattern’s typical horizon. Reported alongside sample size so confidence intervals are legible.
How we will benchmark
Absolute return numbers without a benchmark are meaningless. Every metric above will be reported against three reference portfolios:
SPY — the market baseline. Any strategy below SPY net of effort is failing.
Equal-weighted universe — controls for the universe-selection bias (our 234 names are curated).
Fama-French 5-factor portfolio — controls for known factor exposures so any alpha isn't just re-branded beta.
If the composite beats all three over at least a 6-month forward window, the edge is credible. If not, we publish that too.